arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.13635cs.LG
收藏

高效深度学习的低秩优化:在紧凑架构和快速训练之间取得平衡

Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training

University of Electronic Science and Technology of China(电子科技大学)

Xinwei Ou, Zhangxin Chen, Ce Zhu, Yipeng Liu

摘要:

深度神经网络在许多数据处理应用中取得了巨大成功。然而,高计算复杂性和存储成本使得深度学习难以在资源受限的设备上使用,并且它不是环境友好的,并且具有很多功率成本。在本文中,我们专注于有效的深度学习技术的低秩优化。在空间域,通过网络参数的低秩近似压缩深度神经网络,以较少的网络参数直接降低存储需求。在时域中,网络参数可以在几个子空间中训练,这使得能够进行有效的训练以快速收敛。将空间域中的模型压缩归纳为三类,分别为预训练、预设置和压缩感知方法。通过一系列的可集成技术,如稀疏修剪、量化和熵编码,我们可以将它们集成到一个具有较低计算复杂性和存储的集成框架中。除了总结最近的技术进展,我们有两个发现,激励未来的工作:一是有效的排名优于其他稀疏措施的网络压缩。另一个是张量化神经网络的时空平衡。

英文摘要:

Deep neural networks have achieved great success in many data processing applications. However, the high computational complexity and storage cost makes deep learning hard to be used on resource-constrained devices, and it is not environmental-friendly with much power cost. In this paper, we focus on low-rank optimization for efficient deep learning techniques. In the space domain, deep neural networks are compressed by low rank approximation of the network parameters, which directly reduces the storage requirement with a smaller number of network parameters. In the time domain, the network parameters can be trained in a few subspaces, which enables efficient training for fast convergence. The model compression in the spatial domain is summarized into three categories as pre-train, pre-set, and compression-aware methods, respectively. With a series of integrable techniques discussed, such as sparse pruning, quantization, and entropy coding, we can ensemble them in an integration framework with lower computational complexity and storage. Besides of summary of recent technical advances, we have two findings for motivating future works: one is that the effective rank outperforms other sparse measures for network compression. The other is a spatial and temporal balance for tensorized neural networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑